Customer Story:

Qwak used by Lightricks to introduce ML recommendation models

Lightricks is a pioneer in innovative technology that leads to breakthrough moments throughout the creation process. On a mission to push the limits of technology to reimagine the way creators express themselves, the company brings a unique blend of cutting-edge academic research and design to every user experience.
Qwak was brought aboard to enhance Lightricks's existing machine learning operation, which was originally concentrated around image analysis, and enable fast delivery of complex tabular models. The main requirement was to reduce the  engineering dependency to a minimum along with providing full model training and deployment flexibility.

CT/CD
Continous Training Continous Deployment
0
Engineering dependency
Full
Model analytics & monitoring
About Lightricks
Lightricks develops video and image editing mobile apps, known particularly for its selfie-editing app, Facetune.
Industry
Consumer Software
Photo Editing
Content and Social networks
Use Case:
Recommendations engine on user feed page
‍‍
Model Frameworks:
Pytorch
Qwak stack:
Build system
Serving/Hosting
Analytics
Feature Store
"From the get go, it was clear that Qwak understand our needs and requirements. The simplicity of the implementation was impressive"
Shaked Zychlinski
Head of Recommendations @ Lightricks
The Challenge
Developing recommendations engine models required intensive engineering support and building new infrastructure layers
  • Lightricks ML traditionally revolves around image analysis. The team needed to build ML models based on tabular and dynamic data which requires daily training on fresh data.
  • The platform's flexibility was crucial. Lightricks did not want to be locked down to a specific model structure and also needed a centralized way to train, deploy and access models at scale.
  • Lightricks knew that building Infrastructure requires a lot of effort, experience and time. (Build vs Buy blog)
  • Other vendors could not address the requirements of ease of use, speed of onboarding, continuous training & deployment and feature store support.
See it in Action
How Qwak Assisted?
  • Qwak Build provides an easy way to train the models on fresh data from the feature store and keep each model version metrics in a centralized repository for tracking and review.
  • Qwak Serving provides simple deployment of real-time & batch models with the ability for gradual deployment (canary deployment). 
  • Qwak feature store  provides a simple API  for feature extraction retrieval of features for training. This allows the data science team to work autonomously and modify model inputs without the need to make backend modifications. It also provides the ability to share feature sets between different models and train multiple models at scale.
  • Qwak's Anlytics allows reviewing the model predictions data and creating dashboards on top of the real time data.
  • Qwak's Monitoring provides immediate identification of potential issues and alerts which is critical for real time production platforms.
"Automatic deployment and continuous training were crucial to allow us to scale. Qwak gave us a type of "Jenkins" for machine learning."
Shaked Zychlinski
Head of Recommendations @ Lightricks

Learn More About The Qwak Platform

 
Learn More